mlsanityData to 7 Oct 2026

Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization

arXiv 2106.06485 ↗First posted 11 Jun 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention (VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets (RAP, RAPv2, and PA-100K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 11 Jun 2021.

Builds on

31 of 55 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2019Searching for MobileNetV3cited by 1,984
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  9. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  10. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  11. 2017Improving Person Re-identification by Attribute and Identity Learningcited by 95
  12. 2017HydraPlus-Net: Attentive Deep Features for Pedestrian Analysiscited by 89
19 more
  1. 2017Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classificationcited by 85
  2. 2018Deep Imbalanced Attribute Classification using Visual Attention Aggregationcited by 56
  3. 2019Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localizationcited by 45
  4. 2020SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentationcited by 39
  5. 2020Set-Constrained Viterbi for Set-Supervised Action Segmentationcited by 35
  6. 2016A Richly Annotated Dataset for Pedestrian Attribute Recognitioncited by 33
  7. 2017Attribute Recognition by Joint Recurrent Learning of Context and Correlationcited by 25
  8. 2016Deep Attributes Driven Multi-Camera Person Re-identificationcited by 21
  9. 2018Localization Guided Learning for Pedestrian Attribute Recognitioncited by 21
  10. 2020Rethinking of Pedestrian Attribute Recognition: Realistic Datasets with Efficient Methodcited by 17
  11. 2014Pedestrian Detection aided by Deep Learning Semantic Taskscited by 16
  12. 2015Multi-view Face Detection Using Deep Convolutional Neural Networkscited by 11
  13. 2019Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanismcited by 11
  14. 2017Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Modelcited by 10
  15. 2018Learning View-Specific Deep Networks for Person Re-Identificationcited by 5
  16. 2020An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognitioncited by 4
  17. 2020Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognitioncited by 4
  18. 2020Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypointscited by 4
  19. 2020Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selectioncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 2; 2025: 1.

8 papers.

  1. 2022Deep Gradient Learning for Efficient Camouflaged Object Detectioncited by 65
  2. 2023Disambiguated Attention Embedding for Multi-Instance Partial-Label Learningcited by 9
  3. 2023PrObeD: Proactive Object Detection Wrappercited by 7
  4. 2022Parsing Objects at a Finer Granularity: A Surveycited by 2
  5. 2024Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learningcited by 2
  6. 2025ViTA-PAR: Visual and Textual Attribute Alignment with Attribute Prompting for Pedestrian Attribute Recognitioncited by 2
  7. 2022Reinforced Pedestrian Attribute Recognition with Group Optimization Rewardcited by 0
  8. 2024Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflagecited by 0